Compare · ModelsLive · 2 picked · head to head
DeepSeek V4.1 Flash vs gpt-oss-120b
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
DeepSeek V4.1 Flash wins on 15/15 benchmarks
DeepSeek V4.1 Flash wins 15 of 15 shared benchmarks. Leads in speed · agentic · knowledge.
Category leads
speed·DeepSeek V4.1 Flashagentic·DeepSeek V4.1 Flashknowledge·DeepSeek V4.1 Flashgeneral·DeepSeek V4.1 Flashmath·DeepSeek V4.1 Flash
Hype vs Reality
Attention vs performance
DeepSeek V4.1 Flash
#97 by perf·#4 by attention
gpt-oss-120b
#140 by perf·no signal
Best value
DeepSeek V4.1 Flash
1.3x better value than gpt-oss-120b
DeepSeek V4.1 Flash
175.1 pts/$
$0.31/M
gpt-oss-120b
131.5 pts/$
$0.38/M
Vendor risk
Mixed exposure
One or more vendors flagged
DeepSeek
$3.4B·Tier 1
OpenAI
$840.0B·Tier 1
Head to head
15 benchmarks · 2 models
DeepSeek V4.1 Flashgpt-oss-120b
Artificial Analysis · CritPt
DeepSeek V4.1 Flash leads by +13.2
DeepSeek V4.1 Flash
14.3
gpt-oss-120b
1.1
Artificial Analysis · GDPval
DeepSeek V4.1 Flash leads by +49.6
DeepSeek V4.1 Flash
55.0
gpt-oss-120b
5.4
Artificial Analysis · Humanity's Last Exam
DeepSeek V4.1 Flash leads by +19.6
DeepSeek V4.1 Flash
39.2
gpt-oss-120b
19.6
Artificial Analysis · Long Context Reasoning
DeepSeek V4.1 Flash leads by +32.0
DeepSeek V4.1 Flash
84.0
gpt-oss-120b
52.0
Artificial Analysis · Quality Index
DeepSeek V4.1 Flash leads by +27.9
DeepSeek V4.1 Flash
39.5
gpt-oss-120b
11.6
Artificial Analysis · SciCode
DeepSeek V4.1 Flash leads by +17.9
DeepSeek V4.1 Flash
51.9
gpt-oss-120b
34.0
APEX-Agents
DeepSeek V4.1 Flash leads by +34.8
APEX-Agents · evaluates AI agents on complex, multi-step tasks requiring planning, tool use, and autonomous decision-making in realistic environments.
DeepSeek V4.1 Flash
39.5
gpt-oss-120b
4.7
Chess Puzzles
DeepSeek V4.1 Flash leads by +29.5
Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.
DeepSeek V4.1 Flash
45.3
gpt-oss-120b
15.8
Dtbench
DeepSeek V4.1 Flash leads by +22.7
DeepSeek V4.1 Flash
83.1
gpt-oss-120b
60.5
GPQA diamond
DeepSeek V4.1 Flash leads by +22.4
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
DeepSeek V4.1 Flash
90.0
gpt-oss-120b
67.7
Lmca
DeepSeek V4.1 Flash leads by +29.2
DeepSeek V4.1 Flash
55.3
gpt-oss-120b
26.1
Mystery Game Puzzles
DeepSeek V4.1 Flash leads by +37.2
DeepSeek V4.1 Flash
37.2
gpt-oss-120b
0.0
OTIS Mock AIME 2024-2025
DeepSeek V4.1 Flash leads by +9.5
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
DeepSeek V4.1 Flash
98.3
gpt-oss-120b
88.9
SimpleQA Verified
DeepSeek V4.1 Flash leads by +29.0
SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information.
DeepSeek V4.1 Flash
42.9
gpt-oss-120b
13.9
Surface Evolver Bench
DeepSeek V4.1 Flash leads by +21.3
DeepSeek V4.1 Flash
46.3
gpt-oss-120b
25.0
Full benchmark table
| Benchmark | DeepSeek V4.1 Flash | gpt-oss-120b |
|---|---|---|
Artificial Analysis · CritPt | 14.3 | 1.1 |
Artificial Analysis · GDPval | 55.0 | 5.4 |
Artificial Analysis · Humanity's Last Exam | 39.2 | 19.6 |
Artificial Analysis · Long Context Reasoning | 84.0 | 52.0 |
Artificial Analysis · Quality Index | 39.5 | 11.6 |
Artificial Analysis · SciCode | 51.9 | 34.0 |
APEX-Agents APEX-Agents · evaluates AI agents on complex, multi-step tasks requiring planning, tool use, and autonomous decision-making in realistic environments. | 39.5 | 4.7 |
Chess Puzzles Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities. | 45.3 | 15.8 |
Dtbench | 83.1 | 60.5 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 90.0 | 67.7 |
Lmca | 55.3 | 26.1 |
Mystery Game Puzzles | 37.2 | 0.0 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 98.3 | 88.9 |
SimpleQA Verified SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information. | 42.9 | 13.9 |
Surface Evolver Bench | 46.3 | 25.0 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $0.05 | $0.57 | 1.0M tokens (~524 books) | $1.80 | |
| $0.15 | $0.60 | 131K tokens (~66 books) | $2.62 |